Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
oabi
/
math_ultrachatmistral32_4_3
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
Generated from Trainer
alignment-handbook
HuggingFaceH4/ultrafeedback_binarized
trl
dpo
conversational
text-generation-inference
arxiv:
2305.18290
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
math_ultrachatmistral32_4_3
/
training_DATA
/
plots
823 kB
1 contributor
History:
2 commits
oabi
Model save
5d78f2a
verified
4 months ago
barycenters_delta.png
73.2 kB
Model save
4 months ago
distribution_step_0.png
Safe
27.2 kB
Training in progress, step 24
4 months ago
distribution_step_12.png
25.2 kB
Training in progress, step 24
4 months ago
distribution_step_16.png
25.2 kB
Training in progress, step 24
4 months ago
distribution_step_18.png
26.3 kB
Model save
4 months ago
distribution_step_24.png
26 kB
Model save
4 months ago
distribution_step_4.png
26.5 kB
Training in progress, step 24
4 months ago
distribution_step_6.png
25.7 kB
Model save
4 months ago
distribution_step_8.png
26.9 kB
Training in progress, step 24
4 months ago
log_ratios_evolution.png
82.8 kB
Model save
4 months ago
loss_evolution.png
46.9 kB
Model save
4 months ago
qq_plots_evolution.png
112 kB
LFS
Model save
4 months ago
qq_plots_step_16.png
71.4 kB
Training in progress, step 24
4 months ago
qq_plots_step_24.png
74.6 kB
Model save
4 months ago
quantile_percentile_all_step_16.png
71.3 kB
Training in progress, step 24
4 months ago
quantile_percentile_all_step_24.png
82.3 kB
Model save
4 months ago